Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Layout handling #21

Merged
merged 11 commits into from
Apr 26, 2024
Merged

Add Layout handling #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
2922ab6
add layout information
rue-a Apr 12, 2024
9604759
handle LAYOUT_FIGURE and add custom attributes
rue-a Apr 12, 2024
fd2e5fb
Update textract2page/convert_aws.py
rue-a Apr 15, 2024
c23a8ed
Update textract2page/convert_aws.py
rue-a Apr 15, 2024
b41709a
update tests
rue-a Apr 15, 2024
0d39751
ensure python 3.7 compatibility
rue-a Apr 15, 2024
bf76374
update
rue-a Apr 15, 2024
6062904
add nd ex
rue-a Apr 23, 2024
a267e02
fix table cell creation, refactor reading order generation, remove 'p…
rue-a Apr 24, 2024
19689ff
fix test filename
rue-a Apr 26, 2024
c716c6c
Merge remote-tracking branch 'origin/master' into layouts
rue-a Apr 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,4 +6,5 @@ dist
*~
.vscode
ocrd.log
ocr_test
tests/workspace/OCR-D-IMG
tests/workspace/OCR-D-SEG-PAGE
3 changes: 2 additions & 1 deletion tests/test_workspace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,13 @@ def setUp(self):
{
"aws": Path("textract_responses")
/ f"{filename.name.split('.', 1)[0]}.json",
"img": Path("images") / filename,
"img": Path("images") / filename.name,
"xml": Path("reference_page_xml")
/ f"{filename.name.split('.', 1)[0]}.xml",
}
for filename in (workspace / "images").iterdir()
]
print(self.test_path_dict)

def test_api(self):
for path in self.test_path_dict:
Expand Down
Binary file added tests/workspace/images/nd1969-01-21_3.jpg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added tests/workspace/images/nowa_doba.jpg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
42 changes: 32 additions & 10 deletions tests/workspace/mets.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/v2/premis-v2-0.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mix/v10 http://www.loc.gov/standards/mix/mix10/mix10.xsd">
<mets:metsHdr CREATEDATE="2023-06-21T13:50:00.807482">
<mets:metsHdr CREATEDATE="2024-04-24T11:11:46.027506">
<mets:agent TYPE="OTHER" OTHERTYPE="SOFTWARE" ROLE="CREATOR">
<mets:name>ocrd/core v2.51.0</mets:name>
<mets:name>ocrd/core v2.63.3</mets:name>
</mets:agent>
</mets:metsHdr>
<mets:dmdSec ID="DMDLOG_0001">
Expand All @@ -18,30 +18,42 @@
<mets:fileSec>
<mets:fileGrp USE="OCR-D-IMG">
<mets:file ID="OCR-D-IMG_f18xx-Missio-EMU-0042" MIMETYPE="image/jpeg">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="images/18xx-Missio-EMU-0042.jpg"/>
<mets:FLocat xlink:href="images/18xx-Missio-EMU-0042.jpg" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-IMG_Ansiedlung_Korotschin_UZS_Sign_22a_0018" MIMETYPE="image/tiff">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="images/Ansiedlung_Korotschin_UZS_Sign_22a_0018.tif"/>
<mets:FLocat xlink:href="images/Ansiedlung_Korotschin_UZS_Sign_22a_0018.tif" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-IMG_Ansiedlung_WD_Wielun_Lentschütz_0053" MIMETYPE="image/tiff">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="images/Ansiedlung_WD_Wielun_Lentschütz_0053.tif"/>
<mets:FLocat xlink:href="images/Ansiedlung_WD_Wielun_Lentschütz_0053.tif" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-IMG_Lodz_UZS_25_0056" MIMETYPE="image/tiff">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="images/Lodz_UZS_25_0056.tif"/>
<mets:FLocat xlink:href="images/Lodz_UZS_25_0056.tif" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-IMG_nd1969-01-21_3" MIMETYPE="image/jpeg">
<mets:FLocat xlink:href="images/nd1969-01-21_3.jpg" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-IMG_nowa_doba" MIMETYPE="image/jpeg">
<mets:FLocat xlink:href="images/nowa_doba.jpg" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
</mets:fileGrp>
<mets:fileGrp USE="OCR-D-SEG-PAGE">
<mets:file ID="OCR-D-SEG-PAGE_f18xx-Missio-EMU-0042" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="page/18xx-Missio-EMU-0042.xml"/>
<mets:FLocat xlink:href="reference_page_xml/18xx-Missio-EMU-0042.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-SEG-PAGE_Ansiedlung_Korotschin_UZS_Sign_22a_0018" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="page/Ansiedlung_Korotschin_UZS_Sign_22a_0018.xml"/>
<mets:FLocat xlink:href="reference_page_xml/Ansiedlung_Korotschin_UZS_Sign_22a_0018.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-SEG-PAGE_Ansiedlung_WD_Wielun_Lentschütz_0053" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="page/Ansiedlung_WD_Wielun_Lentschütz_0053.xml"/>
<mets:FLocat xlink:href="reference_page_xml/Ansiedlung_WD_Wielun_Lentschütz_0053.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-SEG-PAGE_Lodz_UZS_25_0056" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="page/Lodz_UZS_25_0056.xml"/>
<mets:FLocat xlink:href="reference_page_xml/Lodz_UZS_25_0056.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-SEG-PAGE_nd1969-01-21_03" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat xlink:href="reference_page_xml/nd1969-01-21_03.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
<mets:file ID="OCR-D-SEG-PAGE_nowa_doba" MIMETYPE="application/vnd.prima.page+xml">
<mets:FLocat xlink:href="reference_page_xml/nowa_doba.xml" LOCTYPE="OTHER" OTHERLOCTYPE="FILE"/>
</mets:file>
</mets:fileGrp>
</mets:fileSec>
Expand All @@ -63,6 +75,16 @@
<mets:fptr FILEID="OCR-D-IMG_Lodz_UZS_25_0056"/>
<mets:fptr FILEID="OCR-D-SEG-PAGE_Lodz_UZS_25_0056"/>
</mets:div>
<mets:div TYPE="page" ID="nd1969-01-21_3">
<mets:fptr FILEID="OCR-D-IMG_nd1969-01-21_3"/>
</mets:div>
<mets:div TYPE="page" ID="nowa_doba">
<mets:fptr FILEID="OCR-D-IMG_nowa_doba"/>
<mets:fptr FILEID="OCR-D-SEG-PAGE_nowa_doba"/>
</mets:div>
<mets:div TYPE="page" ID="nd1969-01-21_03">
<mets:fptr FILEID="OCR-D-SEG-PAGE_nd1969-01-21_03"/>
</mets:div>
</mets:div>
</mets:structMap>
</mets:mets>
Loading
Loading